INDEX

Explanations

mentions of cafes or coffee shops

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nat

-0.17

nan

-0.16

hyp

-0.15

 Guerrero

-0.15

usted

-0.14

 trav

-0.14

ob

-0.14

lashes

-0.14

istrovstvÃŃ

-0.13

 advanced

-0.13

POSITIVE LOGITS

anova

0.17

arian

0.16

presso

0.16

á»ĭ

0.15

-thumb

0.14

 Highlander

0.14

itmap

0.14

ivate

0.14

ritte

0.14

 Morm

0.14

Activations Density 0.007%

mentions of cafes or coffee shops

No Comments

No Known Activations